© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5091
    Prev
    Next
    INDEX
    Explanations

    borders and boundaries

    np_acts-logits-general · gemini-2.5-flash-lite

    ethical boundaries and communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    驷
    0.40
     लीवर
    0.39
    谒
    0.38
     dSample
    0.38
    သေး
    0.38
     coalgebras
    0.38
    ädt
    0.37
    ナット
    0.37
    癱
    0.36
    婶
    0.36
    POSITIVE LOGITS
     borders
    4.00
     boundary
    3.95
     border
    3.94
     boundaries
    3.92
    边界
    3.86
    boundary
    3.67
    boundaries
    3.64
    border
    3.59
    borders
    3.58
     границы
    3.56
    Activations Density 0.231%

    No Known Activations